• 한국전자통신학회논문지
• /
• 제18권5호
• /
• pp.785-796
• /
• 2023

본 연구에서는 구조물 건전성 모니터링에 널리 활용되고 있는 PVDF(: Polyvinylidene fluoride) 센서에 나타날 수 있는 결함을 실시간으로 분류 및 예측하기 위한 방법론을 제안하였다. 센서 부착 환경에 따라 나타나는 센서의 결함 유형을 분류하였고, 임팩트 해머를 이용한 충격 시험을 수행하여 결함 유형에 따른 출력 신호를 획득하였다. 결함 유형에 따른 출력 신호간의 차이를 식별하기 위해 이들의 시간영역 통계 특징을 추출하여 데이터 집합을 구축하였다. 머신러닝 기반 분류 알고리즘들 중 센서 결함 유형 감지에 가장 적합한 알고리즘 선정을 위해 구축한 데이터 집합의 학습 및 이에 따른 결과를 분석하였고, 이들 중 SVM(: Support vector machine)이 가장 높은 성능을 보임을 확인하였다. 선정된 SVM 알고리즘의 추가적인 정확도 향상을 위해 하이퍼 파라미터 최적화 작업을 수행하였으며, 결과적으로 92.5%의 정확도로 센서 결함 유형을 분류하였고 이는 타 분류 알고리즘에 비하여 최대 13.95% 높은 정확도를 보였다. 본 연구에서 제안한 센서 결함 예측 기법은 PVDF 센서뿐만 아니라 실시간 구조물 건전성 모니터링을 위한 다양한 센서의 신뢰성을 확보하기 위한 기반 기술로 활용될 수 있을 것으로 사료된다.

• 한국소음진동공학회논문집
• /
• 제24권7호
• /
• pp.555-561
• /
• 2014

Acoustic Emission technique is widely applied to develop the early fault detection system, and the problem about a signal processing method for AE signal is mainly focused on. In the signal processing method, envelope analysis is a useful method to evaluate the bearing problems and wavelet transform is a powerful method to detect faults occurred on rotating machinery. However, exact method for AE signal is not developed yet for the rotating machinery diagnosis. Therefore, in this paper two methods which are processed by Hilbert transform and DET for feature extraction. In addition, we evaluate the classification performance with varying the parameter from 2 to 15 for feature selection DET, 0.01 to 1.0 for the RBF kernel function of SVR, and the proposed algorithm achieved 94 % classification of averaged accuracy with the parameter of the RBF 0.08, 12 feature selection.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2012년도 제42회 동계 정기 학술대회 초록집
• /
• pp.239-240
• /
• 2012

With advancements in semiconductor device technologies, manufacturing processes are getting more complex and it became more difficult to maintain tighter process control. As the number of processing step increased for fabricating complex chip structure, potential fault inducing factors are prevail and their allowable margins are continuously reduced. Therefore, one of the key to success in semiconductor manufacturing is highly accurate and fast fault detection and classification at each stage to reduce any undesired variation and identify the cause of the fault. Sensors in the equipment are used to monitor the state of the process. The idea is that whenever there is a fault in the process, it appears as some variation in the output from any of the sensors monitoring the process. These sensors may refer to information about pressure, RF power or gas flow and etc. in the equipment. By relating the data from these sensors to the process condition, any abnormality in the process can be identified, but it still holds some degree of certainty. Our hypothesis in this research is to capture the features of equipment condition data from healthy process library. We can use the health data as a reference for upcoming processes and this is made possible by mathematically modeling of the acquired data. In this work we demonstrate the use of recurrent neural network (RNN) has been used. RNN is a dynamic neural network that makes the output as a function of previous inputs. In our case we have etch equipment tool set data, consisting of 22 parameters and 9 runs. This data was first synchronized using the Dynamic Time Warping (DTW) algorithm. The synchronized data from the sensors in the form of time series is then provided to RNN which trains and restructures itself according to the input and then predicts a value, one step ahead in time, which depends on the past values of data. Eight runs of process data were used to train the network, while in order to check the performance of the network, one run was used as a test input. Next, a mean squared error based probability generating function was used to assign probability of fault in each parameter by comparing the predicted and actual values of the data. In the future we will make use of the Bayesian Networks to classify the detected faults. Bayesian Networks use directed acyclic graphs that relate different parameters through their conditional dependencies in order to find inference among them. The relationships between parameters from the data will be used to generate the structure of Bayesian Network and then posterior probability of different faults will be calculated using inference algorithms.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2012년도 제42회 동계 정기 학술대회 초록집
• /
• pp.241-241
• /
• 2012

Semiconductor industry has been taking the advantage of improvements in process technology in order to maintain reduced device geometries and stringent performance specifications. This results in semiconductor manufacturing processes became hundreds in sequence, it is continuously expected to be increased. This may in turn reduce the yield. With a large amount of investment at stake, this motivates tighter process control and fault diagnosis. The continuous improvement in semiconductor industry demands advancements in process control and monitoring to the same degree. Any fault in the process must be detected and classified with a high degree of precision, and it is desired to be diagnosed if possible. The detected abnormality in the system is then classified to locate the source of the variation. The performance of a fault detection system is directly reflected in the yield. Therefore a highly capable fault detection system is always desirable. In this research, time series modeling of the data from an etch equipment has been investigated for the ultimate purpose of fault diagnosis. The tool data consisted of number of different parameters each being recorded at fixed time points. As the data had been collected for a number of runs, it was not synchronized due to variable delays and offsets in data acquisition system and networks. The data was then synchronized using a variant of Dynamic Time Warping (DTW) algorithm. The AutoRegressive Integrated Moving Average (ARIMA) model was then applied on the synchronized data. The ARIMA model combines both the Autoregressive model and the Moving Average model to relate the present value of the time series to its past values. As the new values of parameters are received from the equipment, the model uses them and the previous ones to provide predictions of one step ahead for each parameter. The statistical comparison of these predictions with the actual values, gives us the each parameter's probability of fault, at each time point and (once a run gets finished) for each run. This work will be extended by applying a suitable probability generating function and combining the probabilities of different parameters using Dempster-Shafer Theory (DST). DST provides a way to combine evidence that is available from different sources and gives a joint degree of belief in a hypothesis. This will give us a combined belief of fault in the process with a high precision.

• 한국정밀공학회지
• /
• 제20권3호
• /
• pp.82-88
• /
• 2003

The nondestructive internal quality evaluation of agricultural products has been strongly required from the needs for individual inspection. Recently, the ultrasonic wave has been considered as a solution fur this problem, and an ultrasonic system was constructed for the ultrasonic NDE of fruits and vegetables in our previous work. In this paper, the practical applicability of our ultrasonic system is tested fur the inspection of internal defects (central cavity) in Atlantic potato. Sound speed and RMS of transmitted ultrasonic wave signal were measured and classification algorithm using 2 dimensional stochastic analysis. was presented. Experimental results showed greater value of sound speed and RMS (root mean square) of transmitted signal in normal samples than in abnormal samples with cavity. Also a stochastic method to distinguish normal and abnormal showed fault detection rate less than 5%.

• 한국항해항만학회지
• /
• 제46권3호
• /
• pp.280-288
• /
• 2022

본 연구는 정상 가동 중에도 회전수가 변하는 기기의 이상 및 고장 진단 방안을 다루고 있다. 회전수가 변함에 따라 비정상적 시계열 특성을 내포한 센서 데이터에 기계학습을 적용할 수 있는 절차를 제시하고자 하였다. 기계학습으로는 k-Nearest Neighbor(k-NN), Support Vector Machine(SVM), Random Forest을 사용하여 이상 및 고장 진단을 수행하였다. 또한 진단 정확성을 비교할 목적으로 이상 감지에 오토인코더, 고장진단에는 합성곱 기반의 Conv1D도 추가로 이용하였다. 비정상적 시계열로부터 통계 및 주파수 속성으로 구성된 시계열 특징 벡터를 추출하고, 추출된 특징 벡터에 정규화 및 차원 축소 기법을 적용하였다. 특징 벡터의 선택과 정규화, 차원 축소 여부에 따라 달라지는 기계학습의 진단 정확도를 비교하였다. 또한, 적용된 학습 알고리즘 별로 초매개변수 최적화 과정과 적층 구조를 설명하였다. 최종적으로 기존의 심층학습과 비교하여, 기계학습도 가변 회전기기의 고장을 정확하게 진단할 수 있는 절차를 제시하였다.

• 한국정보통신학회논문지
• /
• 제25권4호
• /
• pp.515-522
• /
• 2021

본 논문에서는 관형 철탑의 용접부 결함을 상시적으로 감시하기 위하여 초음파 탐상 신호에 대한 기계학습 알고리즘의 적용 방법을 제시하고 분석하였다. 기계학습 방법으로는 유전자 알고리즘에 의한 특징 선택과 서포트 벡터머신을 이용한 탐상 신호 분류 방법을 사용하였다. 특징 선택에서는 30개의 후보 특징들 가운데 피크, 히스토그램 하한 경계, 정규 음로그우도가 선택되었으며, 이들은 결함의 깊이에 따른 신호의 차이를 명확하게 나타내었다. 또한, 선택된 특징들을 서포트 벡터 머신에 적용한 결과 정상 부위와 결함 부위를 완벽하게 분류할 수 있는 것으로 나타났다. 따라서 본 연구의 결과는 향후 초음파 신호 기반 결함 성장 조기 감지시스템의 개발과 이를 통한 에너지 송전 관련 산업에 유용하게 사용될 수 있을 것으로 기대된다.

• Journal of Electrical Engineering and Technology
• /
• 제8권2호
• /
• pp.288-294
• /
• 2013

The diagnosis of motor failures using an on-line method has been the aim of many researchers and studies. Several spectral analysis techniques have been developed and are used to facilitate on-line diagnosis methods in industry. This paper discusses the first application of a motor flux spectral analysis to the identification of broken rotor bar (BRB) faults in induction motors using a multiple signal classification (MUSIC) technique as an on-line diagnosis method. The proposed method measures the leakage flux in the radial direction using a radial flux sensor which is designed as a search coil and is installed between stator slots. The MUSIC technique, which requires fewer number of data samples and has a higher detection accuracy than the traditional fast Fourier transform (FFT) method, then calculates the motor load condition and extracts any abnormal signals related to motor failures in order to identify BRB faults. Experimental results clearly demonstrate that the proposed method is a promising candidate for an on-line diagnosis method to detect motor failures.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2009년도 제38회 동계학술대회 초록집
• /
• pp.413-413
• /
• 2010

In semiconductor manufacturing field, all equipments have various sensors to diagnosis the situations of processes. For increasing the accuracy of diagnosis, hundreds of sensors are emplyed. As sensors provide millions of data, the process diagnosis from them are unrealistic. Besides, in some cases, the results from some data which have same conditions are different. We want to find some information, such as data and knowledge, from the data. Nowadays, fault detection and classification (FDC) has been concerned to increasing the yield. Certain faults and no-faults can be classified by various FDC tools. The uncertainty in semiconductor manufacturing, no-faulty in faulty and faulty in no-faulty, has been caused the productivity to decreased. From the uncertainty, the rough set theory is a viable approach for extraction of meaningful knowledge and making predictions. Reduction of data sets, finding hidden data patterns, and generation of decision rules contrasts other approaches such as regression analysis and neural networks. In this research, a RGB sensor was used for diagnosis plasma instead of optical emission spectroscopy (OES). RGB data has just three variables (red, green and blue), while OES data has thousands of variables. RGB data, however, is difficult to analyze by human's eyes. Same outputs in a variable show different outcomes. In other words, RGB data includes the uncertainty. In this research, by rough set theory, decision rules were generated. In decision rules, we could find the hidden data patterns from the uncertainty. RGB sensor can diagnosis the change of plasma condition as over 90% accuracy by the rough set theory. Although we only present a preliminary research result, in this paper, we will continuously develop uncertainty problem solving data mining algorithm for the application of semiconductor process diagnosis.

• 한국정보통신학회논문지
• /
• 제9권7호
• /
• pp.1588-1593
• /
• 2005

본 논문은 정수장에서 사용하는 응집제의 종류를 결정하기 위한 시스템 개발에 관한 내용이다. 정수장은 여러 단위 처리장으로 구성되며, 불순물을 제거하기 위하여 혼화지에서 응집제를 주입하여 침전을 시킨다. 현재까지 응집제 결정을 위해 Jar-test를 이용하는데, 이 방법은 사람의 주관적인 판단에 의존하므로 실험 오차가 발생할 수 있다. 특히 정수장의 자동화를 위한 시스템 개발에서 가장 큰 걸림돌로 작용하고 있다. 본 논문은 이러한 문제점을 해결하기 위하여 로드맵에 기초한 데이터마이닝 기법을 이용하여 응집제를 선택할 수 있는 제어기를 개발하였다. 제어 규칙은 클러스터링 기법으로 도출하였는데, 군집의 초기 값과 개수는 통계적 지수 값을 사용하여 결정하였다.